
Ponytail Gain
Shows you a compact ASCII scoreboard of ponytail's benchmark impact: 80–94% fewer lines, 47–77% lower cost, 3–6× faster, pulled from measured medians across five everyday tasks and three models. It's a one-shot display triggered by /ponytail-gain or "show ponytail impact," not a persistent mode. The honest part: it won't claim per-repo savings because you never wrote the bloated version to compare against. Instead it points you to /ponytail-debt for actual deferred shortcuts in your codebase. Use it when you need to explain the method's leverage to someone, or remind yourself why you're writing less.
- skills.sh installs
- 50.3K
- GitHub stars
- 187.8K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add dietrichgebert/ponytail --skill ponytail-gain --agent claude-codeInstalls into .claude/skills of the current project.
Files
Ponytail Gain
Display this scoreboard when invoked. One-shot: do NOT change mode, write flag files, or persist anything.
The figures are the published agentic benchmark of Ponytail 5: headless Claude
Code (Opus 5.5, default effort) on 39 tasks (feature tickets in a real FastAPI +
React repo, bug fixes, security and privacy cases, small apps), 5 runs each,
against the same agent without the skill. 18 of the tasks have hidden checks
for correctness and safety. Each figure is the geometric mean of the per-task
medians. They are measured, not computed from the current repo.
Source: benchmarks/results/2026-10-07-agentic.md and the README.
Scoreboard
Render plain ASCII bars. The bar length shows ponytail as a share of the no-skill baseline; the label carries the exact figure:
ponytail gain benchmark · 39 tasks × 5 runs · Opus 5.5
Sponsors
Details
- Repository
- github.com/dietrichgebert/ponytail
- Category
- Code Review & Quality
- First seen
- Jul 14, 2026